The call, up front. The sensor was never the problem. Home-based rehab motion tracking already tracks change as well as a clinician, but a systematic over-read of the absolute angle, up to ~20 degrees, is what blocks clinical-grade adoption. The gap is a calibration layer, not a better camera.
The gap
A camera-only system (no sensors strapped to the body) that agrees with the clinical gold standard (a hand-held angle gauge, the goniometer) at 0.85–0.97 is already good enough to track a patient’s progress. What it cannot do is state a defensible absolute angle. And reimbursement, its standing as a regulated medical device (the “software as a medical device”, or SaMD, class), and clinician trust all hang on the absolute number.
Spend on a per-home calibration protocol, not a better sensor. The relative-accuracy problem is already solved; the absolute offset is the whole barrier to a clinical claim.
Source: Lee et al., 'Reliability and Validity of a Single-Camera Markerless Motion Capture System,' Sensors, 2025
Upper limit of the gap (degrees) between single-camera tracking and the manual angle gauge, by shoulder movement (Lee et al., Sensors, 2025). Agreement on relative movement is excellent (0.85–0.97), but the camera consistently reads higher in absolute terms across every movement, so the real blocker is the offset, not the tracking.
Source: GAPTIQ engine: challenge decomposition
- 2012Reflexion Health pilots a Kinect-based knee-PT tool: concept proven, absolute accuracy unaddressed
- 2015A randomized trial (RCT) shows in-home telerehab works as well as face-to-face care after knee replacement
- 2022CMS (the US Medicare agency) adds Remote Therapeutic Monitoring billing codes: money now rides on a defensible number
- 2025Peer review measures the leftover gap: agreement is excellent, but the camera over-reads the absolute angle by +18–20°
Source: ClinicalTrials.gov; Moffet et al. (JBJS) 2015; CMS; Lee et al. 2025
It can already see the movement. It just can’t yet name the angle.
GAPTIQ Signal · Jun 2026
The move
The whitespace is a calibration-and-validation layer that turns a consumer-grade reading into a measurement solid enough to clear the medical-device bar (SaMD), sold to the digital-rehab platforms that already have the cameras and the patients. Whoever owns the calibration owns the clinical claim.
Source: Reliability and Validity of a Single-Camera Markerless Motion Capture System for Shoulder Range of Motion, Sensors (Basel), 2025. Surfaced by the GAPTIQ engine.
